On the convergence of optimistic policy iteration for stochastic shortest path problem

2018/08/27 by Yuanlong Chen, Chen, Yuanlong · 2 citations
Computer Science · Mathematics · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #cs.LG #stat.ML

paper · pdf · doi:10.48550/arxiv.1808.08763

13 pages

arxiv created 2018/08/30 · arxiv updated 2018/08/31

Abstract

In this paper, we prove some convergence results of a special case of optimistic policy iteration algorithm for stochastic shortest path problem. We consider both Monte Carlo and TD(λ) methods for the policy evaluation step under the condition that the termination state will eventually be reached almost surely.

Cited by

• Stochastic Path Planning in Correlated Obstacle Fields
• Convergence of Monte Carlo Optimistic Policy Iteration: Beyond Uniform State-Action Updates

Related

• On the Convergence of Reinforcement Learning with Monte Carlo Exploring Starts
• Proper Policies in Infinite-State Stochastic Shortest Path Problems
• Variations on the Stochastic Shortest Path Problem
• Suboptimality Bounds for Stochastic Shortest Path Problems
• Convergent Reinforcement Learning Algorithms for Stochastic Shortest Path Problem